Resnet Model Developed

Backend/.ipynb_checkpoints/SF__Dinuka_Pest_Damages_identification_V01-checkpoint.ipynb

@@ -249,7 +249,75 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "🟢 ResNetModel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Import Dependencies\n",
+    "import tensorflow as tf\n",
+    "import tensorflow_hub as hub\n",
+    "from tensorflow.keras import layers\n",
+    "from tensorflow.keras.layers import Conv2D , MaxPool2D , Dense , Flatten"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_model(model_url , num_classes=3):\n",
+    "\n",
+    "  feature_extractor_layer = hub.KerasLayer(model_url,\n",
+    "                                           trainable = False, #freeze the already learned patterns \n",
+    "                                           name = \"feature_extraction_layer\",\n",
+    "                                           input_shape = (448, 448,3)) \n",
+    "  #Create our own model\n",
+    "  model  =  tf.keras.Sequential([\n",
+    "    feature_extractor_layer,\n",
+    "    \n",
+    "    layers.Dense(num_classes , activation=\"softmax\" , name=\"output_layer\")\n",
+    "  ])\n",
+    "\n",
+    "  return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "resnet_url = \"https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/5\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Create Resnet Model\n",
+    "resnet_model =  create_model(resnet_url , \n",
+    "                             num_classes = 3)\n",
+    "#Compile our resnet model\n",
+    "resnet_model.compile(loss='categorical_crossentropy',\n",
+    "                     optimizer = tf.keras.optimizers.Adam(),\n",
+    "                     metrics=[\"accuracy\"])\n",
+    "#Fitting the model\n",
+    "resnet_hist = resnet_model.fit(train_data,\n",
+    "                               epochs=15,\n",
+    "                               steps_per_epoch=len(train_data),\n",
+    "                               validation_data = test_data,\n",
+    "                               validation_steps = len(test_data)\n",
+    "                               )"
+   ]
   }
  ],
  "metadata": {

Backend/SF__Dinuka_Pest_Damages_identification_V01.ipynb

@@ -249,7 +249,75 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "🟢 ResNetModel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Import Dependencies\n",
+    "import tensorflow as tf\n",
+    "import tensorflow_hub as hub\n",
+    "from tensorflow.keras import layers\n",
+    "from tensorflow.keras.layers import Conv2D , MaxPool2D , Dense , Flatten"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_model(model_url , num_classes=3):\n",
+    "\n",
+    "  feature_extractor_layer = hub.KerasLayer(model_url,\n",
+    "                                           trainable = False, #freeze the already learned patterns \n",
+    "                                           name = \"feature_extraction_layer\",\n",
+    "                                           input_shape = (448, 448,3)) \n",
+    "  #Create our own model\n",
+    "  model  =  tf.keras.Sequential([\n",
+    "    feature_extractor_layer,\n",
+    "    \n",
+    "    layers.Dense(num_classes , activation=\"softmax\" , name=\"output_layer\")\n",
+    "  ])\n",
+    "\n",
+    "  return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "resnet_url = \"https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/5\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Create Resnet Model\n",
+    "resnet_model =  create_model(resnet_url , \n",
+    "                             num_classes = 3)\n",
+    "#Compile our resnet model\n",
+    "resnet_model.compile(loss='categorical_crossentropy',\n",
+    "                     optimizer = tf.keras.optimizers.Adam(),\n",
+    "                     metrics=[\"accuracy\"])\n",
+    "#Fitting the model\n",
+    "resnet_hist = resnet_model.fit(train_data,\n",
+    "                               epochs=15,\n",
+    "                               steps_per_epoch=len(train_data),\n",
+    "                               validation_data = test_data,\n",
+    "                               validation_steps = len(test_data)\n",
+    "                               )"
+   ]
   }
  ],
  "metadata": {